Generating Questions Based on Semi-Automated and End-to-End Neural Network

With the emergence of large-scale knowledge base,how to use triple information to generate natural questions is a key technology in question answering systems.The traditional way of generating questions require a lot of manual intervention and produce lots of noise.To solve these problems,we propose a joint model based on semi-automated model and End-to-End neural network to automatically generate questions.The semi-automated model can generate question templates and real questions combining the knowledge base and center graph.The End-to-End neural network directly sends the knowledge base and real questions to BiLSTM network.Meanwhile,the attention mechanism is utilized in the decoding layer,which makes the triples and generated questions more relevant.Finally,the experimental results on SimpleQuestions demonstrate the effectiveness of the proposed approach.

Semi-automated segmentation of magnetic resonance images for thigh skeletal muscle and fat using threshold technique after spinal cord injury

Magnetic resonance imaging is considered the ＂gold standard＂ technique for quantifying thigh muscle and fat cross-sectional area. We have developed a semi-automated technique to segment seven thigh compartments in persons with spinal cord injury. Thigh magnetic resonance images from 18 men（18–50 years old） with traumatic motor-complete spinal cord injury were analyzed in a blinded fashion using the threshold technique. The cross-sectional area values acquired by thresholding were compared to the manual tracing technique. The percentage errors for thigh circumference were（threshold： 170.71 ± 38.67; manual： 169.45 ± 38.27 cm2） 0.74%, subcutaneous adipose tissue（threshold： 65.99±30.79; manual： 62.68 ± 30.22） 5.2%, whole muscle（threshold： 98.18 ± 20.19; manual： 98.20 ± 20.08 cm2） 0.13%, femoral bone（threshold： 6.53 ± 1.09; manual： 6.53 ± 1.09 cm2） 0.64%, bone marrow fat（threshold： 3.12 ± 1.12; manual： 3.1 ± 1.11 cm2） 0.36%, knee extensor（threshold： 43.98 ± 7.66; manual： 44.61 ± 7.81 cm2） 1.78% and % intramuscular fat（threshold： 10.45 ± 4.29; manual： 10.92 ± 8.35%） 0.47%. Collectively, these results suggest that the threshold technique provided a robust accuracy in measuring the seven main thigh compartments, while greatly reducing the analysis time.

Design and Development of a New Lightweight High-speed Stacker

A new lightweight high-speed stacker is designed and developed.Its technical parameters are leading the industry level,which can meet the current requirements for high efficiency of intelligent logistics system.Starting from the key structure of stacker,through the theoretical analysis of the new mechanism and the comparison of the new and old equipment,the advantages of the new mechanism in improving the efficiency and lightweight design of stacker are explained.Through ANSYS Workbench finite element software,the structural strength of the main bearing mechanism is analyzed,and the results show that the strength meets the requirements.

Use of Cost Effective Semi-Automated (Mannual/Micro) MGIT System over BACTEC 960 to Perform First Line Anti-Tuberculosis Drugs Sensitivity Testing

Introduction: Multi-drug resistant tuberculosis (MDR-TB) that is the tuberculosis that is resistant to at least 2 of the first line anti-tuberculosis drugs is fatal infectious disease. Cases of MDR-TB are now increasing with 30,000 cases of MDR-TB reported in 2013 by national TB programme. Rapid diagnosis of MDR-TB is extremely important for rapid treatment of patient and to prevent spread of MDR-TB to other. BACTEC 960 system helps in rapid diagnosis but purchase of expensive instrument for the same is the limitation. However, the same purpose can be solved by use of semi-automated MGIT system. Aims and Objectives: Aim of this study is to do drug sensitivity testing of the first line anti-tuberculosis drugs with the use of semi-automated MGIT systems. 350 newly registered and suspected cases of tuberculosis in tertiary care hospital were included. Samples were processed for digestion and decontamination and inoculated in MGIT tubes and also on LJ medium. Reading was taken using semi-automated MGIT system. Positive tubes were confirmed by rapid test for M. tuberculosis and then drug sensitivity was performed. Result: Out of 350 samples, 62% were sputum;33% were pleural fluid and rest 5% were lymph node, Ascetic fluid, CSF, pus. Average day of positivity by MGIT was 13 - 20 days as compared to 25 - 37 days by solid medium, which was statistically significant with p value Conclusion: Manual MGIT System is a simple, efficient, safe to use diagnostic system. It does not require any expensive/special instrumentation other than the UV lamp for detection of fluorescence. The rapidity by which mycobacteria are detected is the most important advantage of the Manual MGIT. In areas with limited resources where purchase of expensive instruments such as the MGIT960 is out of scope, the use of manual MGIT for rapid susceptibility testing for MDR-TB could be a possibility.

基于数字孪生的矿山散料堆场堆取料机智能监测系统

在许多涉及散料装卸作业的大型储料场中,斗轮堆取料机被视为当前最为理想的大型可连续作业机械,为了延长其使用寿命,降低维修成本并解决人工巡检不便的问题,提出了一种基于五维数字孪生的智能健康监测系统。通过机身外部布设光纤光栅传感器以及内置电机实时运转数据获取堆取料机的当前工作状态,并将数据传入内部信息交互通信网络进行数据的分离存储与融合处理,在消除双光栅由于机械疲劳所带来的温度补偿误差后,构建了多数据融合的、立体化的堆取料机数字健康模型,实现了堆取料机健康状态的智能化预测与立体化监测。通过在秦皇岛港散料矿物储料场的QL6000.55型斗轮堆取料机进行全系统的安装运行,极大促进了料场数字化进程,改变了管理模式,提高了生产效率,直接增加了经济效益。研究表明:该系统能够可靠地提供斗轮取料机的实时工作状态,对基本的故障类型有着一定的预警效果,降低了堆取料机维护的人力与物力投入,为矿区大型机械健康监测提供了有益参考。

基于PLC的全自动码垛机电气控制系统设计研究

自动码垛机需要实现多轴运动控制,包括各种传动部件的精确控制和同步。需要考虑运动规划、速度控制、位置反馈等方面,这使得确保系统的稳定性和精度难度较高。为此,设计基于PLC的全自动码垛机电气控制系统。首先,通过PLC、传感器、执行器、操作面板和人机界面、电源和电气元完成系统的整体硬件的设计;其次,设计自动取料模块和速度电气控制器。对于系统软件部分,先设计PLC梯形图。基于此,结合抗扰电气控制器原理,再设计全自动码垛机的鲁棒电气控制算法。实验结果表明,所设计系统能够精准跟踪全自动码垛机机械臂的关节轨迹,说明该系统的电气控制效果较好,且具有理想的抗干扰性。

堆垛机速度控制策略对比研究

文章分析了自动化立体仓库堆垛机现有的多段调速、速度闭环和位移闭环等控制方式,发现多段调速控制方式具有立柱振幅太大、速度易突变和运行时间长等问题;而单一速度闭环控制系统需要低速运行一段距离,以降低作业效率;位移内嵌速度闭环控制系统虽然定位精确、动态响应快,但速度突变容导致货物倒塌事故。针对以上问题,提出了采用S型速度曲线控制的方式,以提高堆垛机运行的快速性、安全性和定位精度。然后在Matlab/Simulink模块中建立立柱摆动的二阶仿真模型,由仿真比较可得,S型速度曲线控制方式下速度减少了7.6%,振幅降低了8.3%,所以该方式具有更好的快速性、平稳性和定位精度效果,尤其在中长距离的时间优化方面效果明显。

数字孪生驱动的堆垛机模型可视化设计与实现

针对堆垛机研发周期长且其工作过程中信息采集率和工作效率低等问题,提出了基于数字孪生的堆垛机模型可视化设计方法。结合数字孪生技术,基于数字孪生五维模型,利用进程控制对象连接(OLE for Process Control,OPC)统一架构技术搭建堆垛机模型的虚拟调试平台,实现了堆垛机物理模型与数字模型的实时通信和数据交互。通过对堆垛机物理模型工作状态的数据采集,实现了堆垛机工作状态的可视化监测和工作效率的优化,验证了基于数字孪生的堆垛机模型可视化设计方法的可行性。可为堆垛机的研发设计和透明化作业提供参考。

堆取料机卷扬系统的设计与计算

非标设计的卷扬系统是顶堆侧取堆取料中的取料机系统重要组成部门。设计输出拉力不足则可能引起取料臂架倾翻等重大安全事故,设计输出拉力过大则会增加设备成本。本文介绍了卷扬系统的拉力计算过程,着重介绍了双拉绳卷扬系统的规避偏载的方法及结构形式,为确保顶堆侧取堆取料的安全生产,提升产品的经济性提供了借鉴及参考。

立体库堆垛机运行系统优化研究

针对立体库堆垛机的立柱在加减速变化时易出现挠度变形的问题,以单立柱堆垛机为研究对象,基于挠度理论,分析影响立柱产生挠度形变的主要因素;将立柱简化为悬臂梁,推导立柱顶端的摆动方程,并建立Simulink仿真模型;以系统运行效率和稳定性为评价指标,采用遗传算法对堆垛机的速度控制曲线进行多目标优化,并对优化后的速度控制曲线进行仿真分析。研究表明,在堆垛机水平和竖直方向运行到最大距离工况下,优化后的堆垛机运行时间由12.5 s减少至11.621 s,系统的运行效率提升7.03%;最大振幅由5.99 mm减少至5.08 mm,在提高运行效率的前提下,系统的运行稳定性提升了15.2%,降低了堆垛机在运行过程中的挠度形变,验证了优化方法的可行性,可为堆垛机的设计研究提供参考依据。

斗轮堆取料机俯仰结构的有限元分析及优化设计

该文主要探究斗轮堆取料机俯仰结构有限元模型的构建过程、静力分析和优化设计。该文首先使用UG软件构建俯仰结构模型,然后使用HyperMesh软件对该模型进行几何清理与网格划分。在此基础上,设计俯仰结构有限元分析方案,在施加载荷与边界处理后展开静力分析。结果表明,斗轮堆取料机俯仰结构的等效应力远低于容许应力,结构强度达标。随后选取俯仰结构的前臂架,Ansys软件中的Design Explorer模块展开优化设计,将重量作为优化目标。在不改变前臂架最大等效应力的前提下,前臂架的重量从原来的21767 kg变为18240 kg,重量减幅达到16.2%,优化效果明显。

基于改进遗传算法优化堆垛机速度曲线研究

堆垛机是起重运输行业的重要设备,其在计算机系统的控制下,通过轨道在立体仓库里高效、绿色地往返穿梭,精确停在指位置并存取货物。堆垛机以最短时间从静止状态提升至高速运动状态,在保持一段时间后逐渐减速直至停止,由于受到本身结构的影响,堆垛机以何种速度运行成为目前需要解决的问题。文中提出用速度曲线表示堆垛机的运动特性,并对其进行优化研究。传统的速度曲线优化对目标函数有较强的依赖性和严格性,基于权重分析法(AHP)得到堆垛机关键性能指标的权重,提出改进遗传算法(GA)对速度曲线进行优化。仿真结果表明:该算法具有优化精度高、鲁棒性好的优点,在该领域具有良好的参考意义和实用价值。

堆取料机取料过程中防坍塌预警及路径规划研究

在运煤轮船船舱进行取料作业时,由于路径规划可能引发煤堆坍塌的危险,提出一种基于分层点云边缘信息提取的防止煤堆坍塌的模拟堆取料机取料路径规划方法。首先利用搭载二维激光扫描试验装置采集原始三维点云数据,通过坐标转换,采用直通滤波算法去噪滤波,随机采样法简化算法精简点云数据,基于切片法计算煤堆体积和质量,实现对来煤精准盘点;然后提取每层煤料堆表面的边缘信息,将不同层次的煤料堆边缘信息组合起来,构建出整个煤料堆表面的边缘模型,实时计算待取料煤堆边缘安息角,实现煤堆坍塌预警信息;最后基于直线插补方法进行取料路径规划,给出防止煤堆坍塌的模拟堆取料机执行机构作业路径。

基于Simulation的堆垛机启停金属结构分析

堆垛机是智能立体仓储中的核心设备,其运行机构在启停时,由于其自身高度较高,加之立柱上方连接的上横梁组件及立柱间的载货台组件在运行机构启停时惯性力的双重影响下,会产生不同程度的挠度变形,针对双立柱堆垛机进行分析,文中利用Simulation插件对堆垛机金属结构模型进行应力分析,得出金属结构的应力应变的分析结果。

调速技术在堆取料机系统中的应用

堆取料机调速是现代堆取料机设备调试和使用的重要环节。本文根据产品设计与现场实践,结合理论分析,详细阐述了堆取料机的调速原理及实现方法。

基于激光扫描技术的无人化斗轮堆取料机控制方案

针对现有斗轮堆取料机的无人化改造,提出一种基于激光扫描建模的无人化斗轮堆取料机方案。通过激光扫描系统扫描并实时生成堆垛的三维模型,对模型分析进行决策控制,实现斗轮堆取料机的自动化运行,同时保留远程操作功能提高可靠性。该方案实施可减员增效,改善工作环境。

浅析长节距米制输送链条与链轮

非标设计的取料系统是顶堆侧取堆取料机中的重要组成部分。本文详细介绍了驱动链轮组链轮轮齿关键参数,并对链轮齿形优化设计方案进行了介绍,着重阐述非标设备中链条传动的运动特性,总结了链条工作中产生冲击力的原因及减少冲击力的措施,为确保非标设计顶堆侧取堆取料机符合技术要求和提升设备实际使用效果提供了借鉴和参考。